chengzeyi / ParaAttentionLinks
https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
☆342Updated last month
Alternatives and similar repositories for ParaAttention
Users that are interested in ParaAttention are comparing it to the libraries listed below
Sorting:
- Radial Attention Official Implementation☆453Updated last week
- Light Video Generation Inference Framework☆257Updated last week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆566Updated 4 months ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆245Updated last month
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆371Updated 2 months ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆241Updated 7 months ago
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆28Updated 3 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆202Updated 5 months ago
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆393Updated last month
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆698Updated 8 months ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,023Updated last month
- The official code for "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆173Updated 3 weeks ago
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆670Updated this week
- [NeurIPS 2024] Boosting the performance of consistency models with PCM!☆487Updated 7 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆136Updated last month
- Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x fast…☆272Updated 9 months ago
- An out-of-the-box inference acceleration engine for Diffusion and DiT models☆52Updated 4 months ago
- ☆285Updated 7 months ago
- ☆173Updated last week
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆168Updated 4 months ago
- faster parallel inference of mochi-1 video generation model☆124Updated 5 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆68Updated 6 months ago
- Enhance-A-Video: Better Generated Video for Free☆561Updated 4 months ago
- ☆171Updated 6 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆456Updated this week
- Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".☆182Updated 3 months ago
- Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆208Updated 3 months ago
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆350Updated this week
- VGDFR: Diffuison-based Video Generation with Dynamic Frame Rate☆12Updated 2 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆836Updated 2 months ago